# Searching Toward Pareto-Optimal Device-Aware Neural Architectures

arXiv: https://arxiv.org/abs/1808.09830 · HTML: https://mlsanity.com/paper/1808.09830/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2018.

## Built on by (most cited first, 5 of 5)

- [Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs](https://mlsanity.com/paper/2602.10377/) (2026)
- [Pareto-aware Neural Architecture Generation for Diverse Computational Budgets](https://mlsanity.com/paper/2210.07634/) (2022)
- [Pareto-Frontier-aware Neural Architecture Generation for Diverse Budgets](https://mlsanity.com/paper/2103.00219/) (2021)
- [Evolution and Efficiency in Neural Architecture Search: Bridging the Gap Between Expert Design and Automated Optimization](https://mlsanity.com/paper/2403.17012/) (2024)
- [TND-NAS: Towards Non-differentiable Objectives in Progressive Differentiable NAS Framework](https://mlsanity.com/paper/2111.03892/) (2021)

## Abstract (arXiv)

Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding. However, most existing works only optimize for model accuracy and largely ignore other important factors imposed by the underlying hardware and devices, such as latency and energy, when making inference. In this paper, we first introduce the problem of NAS and provide a survey on recent works. Then we deep dive into two recent advancements on extending NAS into multiple-objective frameworks: MONAS and DPP-Net. Both MONAS and DPP-Net are capable of optimizing accuracy and other objectives imposed by devices, searching for neural architectures that can be best deployed on a wide spectrum of devices: from embedded systems and mobile devices to workstations. Experimental results are poised to show that architectures found by MONAS and DPP-Net achieves Pareto optimality w.r.t the given objectives for various devices.